Improved Super-Resolution through Residual Neighbor Embedding

Size: px
Start display at page:

Download "Improved Super-Resolution through Residual Neighbor Embedding"

Transcription

1 Improved Super-Resolution through Residual Neighbor Embedding Tak-Ming Chan 1 and Junping Zhang Shanghai Key Laboratory of Intelligent Information Processing, Department of Computer Science and Engineering, Fudan University, , China { ,jpzhang}@fudan.edu.cn 2 The Key Laboratory of Complex Systems and Intelligence Science Institute of Automation, Chinese Academy of Sciences, Beijing, , China Abstract. In this paper we first present the machine learning methods applied to the single-image super-resolution issue. Reviewing the novel learning approach of super-resolution through neighbor embedding based on training images, we propose an revised method learning about the residuals from different level, inspired by image pyramids from multiresolution processing. Experiments on gray-level and color images show that our revised method yields results with lower Root-Mean-Squared errors and preserves high spatial-frequency information better such as sharp edges and high contrast. 1 Introduction Super-resolution is the problem of generating high-resolution enlargements of pixel-based images from one or multiple low resolution images. Applications include resolution enhancement for digital images such as satellite images and images received via CCTV (Closed Circuit Television) or mobile phone, saving storage for web thumbnail images, viewing low-resolution programs on highdefinition television, etc. Super-resolution also has potential value for the preprocessing of low-resolution input for biometrics applications such as face recognition [1]. Traditional resolution enhancement methods concerning spatial frequency mostly refer to interpolation approaches, bilinear and cubic spline, for example, which are common yet suffer from blurring and perceived loss of details. The reason is that they treat different types of image information with the same manner and smoothing all masked regions no matter they consist of edges or textures. Other than traditional interpolation approaches, recent superresolution algorithms based on machine learning take advantage of manifold learning and training images to preserve spatial-frequency and recover information of details such as edges and textures. From this viewpoint, there is loss of information beyond low-resolution images and the task of super-resolution is to retrieve the missing information correctly from training samples and patterns. There are two primary ways of super-resolution based on machine learning: while generating a high-resolution image from a sequence of low-resolution images (a scene) (e.g., [2, 3]) is referred to as super-resolution, generation from

2 2 a single low-resolution image can be specified as single-frame or single-image super-resolution [4, 5]. In this paper, we focus on the latter way of single-image super-resolution. 2 Single-image Super-Resolution with Machine Learning Some research groups have applied machine learning to address the singleimage super-resolution problem. The well known one among them is William T. Freeman s group in the Artificial Intelligence Lab at Massachusetts Institute Technology. Generally speaking, the main concept of single-image superresolution relies on a carefully selected training set of high-resolution images. The training images are down-sampled, divided up into low-resolution patches, each one forming a training pair with the corresponding high-resolution patch. Such super-resolution algorithms try to learn the connection between the lowresolution patches from test images and the ones from training set, and try to reconstruct the high-resolution target employing the according high-resolution training patches. There is a connection to manifold learning and dimensionality reduction here, implicitly existing between the low-resolution and high-resolution training pairs. But the dimensionality transformation is backward in this problem. We are given low-dimensional image patches and we need to interpolate their high-dimensional counterparts. Different single-image super-resolution approaches share similar concepts as mentioned above, but vary in their ways of choosing effective features, designing mechanisms to find appropriate matching patterns, and so on. Freeman et al presented the method which first generates the high-resolution estimate with traditional interpolation, second finds the missing high-frequency information from training images and finally combine the estimate with high-frequency information to obtain the target image [4]. Kim et al proposed an revised method adapting Kernel Hebbian Algorithm for feature representation which had comparable performance particularly for images of faces and natural scenes [6]. Chang et al brought forward a novel method employing YIQ space and gradients as features, as well as searching more than one nearest neighbors to generate high-resolution patches to yield good reconstructions [5]. 3 Super-Resolution through Neighbor Embedding Since our proposed approach is based on the method of super-resolution through neighbor embedding(srne) [5] and it will be briefly introduced for better understanding our work. Chang et. al. developed this method based loosely on LLE [7]. Generally, they match each given low-resolution test image patch to its k nearest neighbors other than only one neighbor in the low-resolution training set, and then form the high-resolution image patch using a weighted sum of the high-resolution training set. Based on simple geometric intuitions of locally linear embedding, the local geometry of one patch in a low-resolution image can be represented by locally linear weighted sum of its nearest neighbors. And optimal weights can be calculated based on least square criterion. From manifold

3 3 learning point of view, data in low-dimensional subspace should have as similar neighborhood relationship as in corresponding high-dimensional space [8, 9]. So the high-resolution patch can be computed by the weighted sum of the highresolution ones corresponding to those low-resolution nearest neighbors we find. SRNE adopts the ideas, and what s more, it employs elaborate techniques, using 1st and 2nd gradient operators as feature vectors and smoothing overlapped patches. More details can be seen in [5]. 4 Proposed Method Using Residuals Neighbor Embedding Results of SRNE are smooth and rich in textures, however, high spacial-frequency details such as edges are not sharply preserved and the Root-Mean-Squared(RMS) errors can be further reduced, which has the have the formulation of RMSe = ( n (ŷ i y i ) 2 ) 1 2 (1) n i=1 Where ŷ i stands for the values of pixel in the ideal target Y and y i stands for the values of corresponding pixels in output Y t. And n stands for the number of total pixels in Y. For preserving the high frequency details such as sharp edges, we are inspired by the multi-resolution processing, especially the residuals from image pyramids, a collection of images with decreasing resolution arranged in the shape of a pyramid [10]. Instead of only using the luminance(y) component from YIQ color space to find the nearest neighbors, our method applies residuals as feature vectors to super-resolution through neighbor embedding. First input is upsampled by traditional interpolation. Second we choose residuals from various levels of images of multi-resolution to do the matching and thus employ the embedding to generate the high-resolution residual. Third we combine the high-resolution residual and the upsampled input to obtained the final result. Suppose we have to reconstruct the nx (n times in each dimension) magnification Y t for the low-resolution input X t. First,we downsample X t to the lower level image (1/nX of X t ) and employ simple interpolation method (e.g.,neighbor replication or bilinear interpolation) to generate its upsampled nx estimate ˆX t, which remains the same size with X t. Second, we compute the residual ResiX t between X t and ˆX t. Similar processes are applied to Y s and X s, generating ResiY s between Y s and estimate upsampled from X s, as well as ResiX s between X s and estimate ˆX s. Ŷt is also prepared using simple interpolation method on X t. And then the algorithm of neighbor embedding is employed to recover each patch of ResiY t from ResiY s based on the weighted sum of its k nearest neighbors from patch to patch between ResiX t and ResiX s. Finally ResiY t is added to Ŷt to finally obtain the Y t. The pseudo-code of our proposed method is tabulated in Table 1.

4 4 Input: low-resolution image X t, high-resolution training image Y s, number of nearest neighbors k, patch Size s and magnification n. Procedure 1: Residuals Generation 1. Compute the lower level(1/nx of X t) image of low input X t. 2. Upsample the lower level image with interpolation methods(e.g., neighbor interpolation) to get the nx estimate ˆX t. 3. Compute the residual ResiX t between X t and ˆX t. 4. Downsample Y s by 1/nX to obtain X s. 5. Under processes similar to 1, 2 and 3 compute ResiY (s) between Y s and estimate upsampled from X s, ResiX(s) between X s and estimate ˆX s. 6. Upsample X t with interpolation to get the nx estimate Ŷt. Procedure 2: Residual Neighbor Embedding 1. Cut ResiX t and also ResiX s into patches of size s by s with overlapping by one or two pixels. 2. Cut ResiY s into patches of size n s by n s with overlapping by n or n 2 pixels accordingly 3. For each patch resix q t from ResiXt, do { Find k nearest neighbors among all patches from ResiX s Compute the reconstruction weights to minimize the error of reconstructing resix q t Compute the high-resolution embedding resiy q t using the reconstruction weights combining the patches in ResiY s corresponding to the k nearest neighbors in ResiX s. } 4. Enforce local compatibility and smoothness constraints between adjacent patches among all resiy q t and get ResiYt. 5. Y t is obtained by adding ResiY t to Ŷt. Table 1. The Pseudo-code of Our Proposed Method 5 Experiments To evaluate the performance of the proposed approach and compare it with the original SRNE method, we implement gray-level version and color version of the both approaches and experiment results are reported in the following subsections. 5.1 Gray-Level Image Experiments The original SRNE paper [5] only uses Y component of YIQ color space to carry out the algorithm. The other two components are enlarged by replication and simply contribute to the transformation from YIQ back to RGB color space thus they are of little effect in the performance. Concerning this we revise the code to a gray-level image implementation in order to evaluate the two approaches more independently, without the interference of other color components. The revision is straightforward, in which Y component are replaced by the gray-level values(which is also the only luminance) and the transformation of color space is waived for the original method. And within our proposed approach, residuals of the gray-level image are used to perform the neighbor embedding algorithm. We use the same training image for both methods. Several experiments are performed on gray-level images taken from the FERET data base. From the experiment of 4X magnification illustrated in Figure 1, we can see both SRNE and residual approaches yield better reconstruction than bilinear and bi-cubic interpolation. And our method is higher in contrast and

5 5 sharper in edges than SRNE. And another 4X example is shown in Figure 2. The training images for both methods are two other faces taken from the FERET data base, respectively. Fig. 1. 4X magnification of girl s face. Left column: Low-Resolution input. Middle column: Residual ResiY t in our method. Right column: Close-up comparison of different methods. From top to bottom: input(pixels 4X enlarged), true high-resolution target, bilinear, bi-cubic, SRNE, our method. RMS error is another notion to compare different super-resolution methods. In Figure 3 we can see that results of residual neighbor embedding have overall lower RMS errors than original SRNE and k is small when the lowest RMS error is obtained, and it s not very sensitive to different values in both methods. The improvement in RMS error of our method to the original one is as much as that of the original one to simple neighbor replication. 5.2 Color Image Experiments For more intuitive evaluation of the two methods, we also implement the color image experiments based on YIQ color space between SRNE and our residual method. In the original method YIQ color space and Y component are kept as the paper [5] does, while in our proposed method residuals of Y component are adopted to perform the neighbor embedding as Table 1 describes. Finally, images in YIQ space are transformed to RGB space with the same manner. Super-resolution results for the the 3X magnification of the bird image example

6 6 Fig. 2. 4X magnification of man s face. (a)input. (b)true high-resolution target. (c)bicubic interpolation. (d)srne. (e)our method. from the original paper are illustrated in Figure 4. We use exactly the same patch size, overlapping degree and training images as the original paper does. It is also can be seen that both our method and SRNE have better results than traditional interpolation methods. What s more, our method has lower RMS errors and sharper contrast and edges than the original one. Also in another 3X magnification example of the plant image from the original paper, our method outperforms SRNE with RMSe = , compared to RMSe = with the same parameter constraints (Figures are not included to save length). 6 Conclusion and Discussion In this paper, we present the application of machine learning methods for singleimage super-resolution. Based on the main concept of learning from the training

7 RMSe RMSe K K Fig. 3. Comparison of RMS errors given different k values between original Neighbor Embedding (lines with +) and our residual method (lines with *). RMS errors of simple neighbor pixel interpolation are shown with real lines. Left: RMSe of super-resolution for girl s face. Right: RMSe for man s face. set, various methods focus on different ways to choose features and finding candidates. We study the novel method of SRNE and develop an improved method with residuals of multi-resolution image pyramids. The proposed approach is lower in RMS errors and better at recovering the sharp contrast and fine edges. It is promising in improving the neighbor embedding based on machine learning for better performance of super-resolution. Several problems deserve to make further research. First, the implementation of residual neighbor embedding has some requirements on image size for the lower levels have to be computed and they can not be too small on pixel-scale. Second, some block effects appear in the region of constant pixel values, for in such regions there are no residuals existing between estimate and the true image. Some approaches are under research to amend this shortcoming. One way is adopting a more elaborate upsample interpolation (e.g. cubic-spline) to obtain finer residuals. While applying original neighbor embedding to the regions with constant pixel values is another promising approach to smooth and improve the quality of images. Acknowledgement This research is sponsored by NSFC under contract No And the authors are grateful to PhD Hong Chang and Professor Dit-Yan Yeung for generous providing source code and invaluable comments. And Portions of the research in this paper use the Gray Level and Color database of the FERET program. References 1. T. M. Chan and J. Zhang, An Improved Super-Resolution with Manifold Learning and Histogram Matching, Proc. IAPR International Conference on Biometric (ICB-2006), LNCS3832, Springer-Verlag Berlin Heidelberg, 2006, pp

8 8 Fig. 4. 3X magnification of the bird image. (a)input. (b)true high-resolution target. (c)bi-cubic interpolation. (d)srne. RMSe = (e)our method. RMSe = S. Baker and T. Kanade, Limits on Super-Resolution and How to Break Them, IEEE Transactions on Pattern Analysis and Machine Intelligence,vol.24, NO.9, September W. T. Freeman, E.C. Pasztor, and O.T. Carmichael, Learning Low-Level Vision, Intl J. Computer Vision,vol. 40, no. 1, Oct. 2000, pp W. T. Freeman, Thouis R. Jones, and Egon C. Pasztor, Example-Based Super-Resolution, in Proceedings of Computer Graphics and Applications, IEEE, March/April 2002, pp H. Chang, D. Y. Yeung, Y. Xiong, Super-resolution through neighbor embedding, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), vol.1, pp , Washington, DC, USA, 27 June - 2 July K. I. Kim, M. O. Franz, and B. Scholkopf, Kernel Hebbian Algorithm for Single-Frame SuperResolution, Statistical Learning in Computer Vision, ECCV 2004 Workshop, Prague, Czech Republic, May 2004, pp S. T. Roweis and K. S. Lawrance, Nonlinear Dimensionality Reduction by Locally Linear Embedding, Science, 290, pp , J. Zhang, S. Z. Li, and Jue Wang, Manifold Learning and Applications in Recognition, in Intelligent Multimedia Processing with Soft Computing. Yap Peng Tan, Kim Hui Yap, Lipo Wang (Ed.), Springer-Verlag, Heidelberg, J. Zhang, Several Problmes in Manifold Learning, Machine Learning and Applications, ZhiHua Zhou et. al. (Eds.), Tsinghua University Press, R. C. Gonzalez and R. E.Woods, Digital Image Processing(Second Edition), Prentice Hall, 2002, pp P. J. Phillips and H. Moon and S. A. Rizvi and P. J. Rauss, The FERET Evaluation Methodology for Face Recognition Algorithms, IEEE Trans. Pattern Analysis and Machine Intelligence, Volume 22, October 2000, pp

Learning based face hallucination techniques: A survey

Learning based face hallucination techniques: A survey Vol. 3 (2014-15) pp. 37-45. : A survey Premitha Premnath K Department of Computer Science & Engineering Vidya Academy of Science & Technology Thrissur - 680501, Kerala, India (email: premithakpnath@gmail.com)

More information

Enhancing DubaiSat-1 Satellite Imagery Using a Single Image Super-Resolution

Enhancing DubaiSat-1 Satellite Imagery Using a Single Image Super-Resolution Enhancing DubaiSat-1 Satellite Imagery Using a Single Image Super-Resolution Saeed AL-Mansoori 1 and Alavi Kunhu 2 1 Associate Image Processing Engineer, SIPAD Image Enhancement Section Emirates Institution

More information

Transferring Colours to Grayscale Images by Locally Linear Embedding

Transferring Colours to Grayscale Images by Locally Linear Embedding Transferring Colours to Grayscale Images by Locally Linear Embedding Jun Li, Pengwei Hao Department of Computer Science, Queen Mary, University of London Mile End, London, E1 4NS {junjy, phao}@dcs.qmul.ac.uk

More information

Hallucinating Faces: TensorPatch Super-Resolution and Coupled Residue Compensation

Hallucinating Faces: TensorPatch Super-Resolution and Coupled Residue Compensation Hallucinating Faces: TensorPatch Super-Resolution and Coupled Residue Compensation Wei Liu 1, Dahua Lin 1, and Xiaoou Tang 1, 2 1 Department of Information Engineering The Chinese University of Hong Kong,

More information

Super-resolution using Neighbor Embedding of Back-projection residuals

Super-resolution using Neighbor Embedding of Back-projection residuals Super-resolution using Neighbor Embedding of Back-projection residuals Marco Bevilacqua, Aline Roumy, Christine Guillemot SIROCCO Research team INRIA Rennes, France {marco.bevilacqua, aline.roumy, christine.guillemot}@inria.fr

More information

Gabors Help Supervised Manifold Learning

Gabors Help Supervised Manifold Learning Gabors Help Supervised Manifold Learning Junping Zhang 1,, Chao Shen 1, Jufu Feng 2 1 Shanghai Key Laboratory of Intelligent Information Processing Department of Computer Science and Engineering, Fudan

More information

CONTENT ADAPTIVE SCREEN IMAGE SCALING

CONTENT ADAPTIVE SCREEN IMAGE SCALING CONTENT ADAPTIVE SCREEN IMAGE SCALING Yao Zhai (*), Qifei Wang, Yan Lu, Shipeng Li University of Science and Technology of China, Hefei, Anhui, 37, China Microsoft Research, Beijing, 8, China ABSTRACT

More information

Edge-Directed Image Interpolation Using Color Gradient Information

Edge-Directed Image Interpolation Using Color Gradient Information Edge-Directed Image Interpolation Using Color Gradient Information Andrey Krylov and Andrey Nasonov Laboratory of Mathematical Methods of Image Processing, Faculty of Computational Mathematics and Cybernetics,

More information

Single-Image Super-Resolution Using Multihypothesis Prediction

Single-Image Super-Resolution Using Multihypothesis Prediction Single-Image Super-Resolution Using Multihypothesis Prediction Chen Chen and James E. Fowler Department of Electrical and Computer Engineering, Geosystems Research Institute (GRI) Mississippi State University,

More information

Improved Feature Selection for Neighbor Embedding Super-Resolution Using Zernike Moments

Improved Feature Selection for Neighbor Embedding Super-Resolution Using Zernike Moments Improved Feature Selection for Neighbor Embedding Super-Resolution Using Zernike Moments Deepasikha Mishra, Banshidhar Majhi and Pankaj Kumar Sa Abstract This paper presents a new feature selection method

More information

Face Alignment Under Various Poses and Expressions

Face Alignment Under Various Poses and Expressions Face Alignment Under Various Poses and Expressions Shengjun Xin and Haizhou Ai Computer Science and Technology Department, Tsinghua University, Beijing 100084, China ahz@mail.tsinghua.edu.cn Abstract.

More information

Adaptive osculatory rational interpolation for image processing

Adaptive osculatory rational interpolation for image processing Journal of Computational and Applied Mathematics 195 (2006) 46 53 www.elsevier.com/locate/cam Adaptive osculatory rational interpolation for image processing Min Hu a, Jieqing Tan b, a College of Computer

More information

COMPACT AND COHERENT DICTIONARY CONSTRUCTION FOR EXAMPLE-BASED SUPER-RESOLUTION

COMPACT AND COHERENT DICTIONARY CONSTRUCTION FOR EXAMPLE-BASED SUPER-RESOLUTION COMPACT AND COHERENT DICTIONARY CONSTRUCTION FOR EXAMPLE-BASED SUPER-RESOLUTION Marco Bevilacqua Aline Roumy Christine Guillemot Marie-Line Alberi Morel INRIA Rennes, Campus de Beaulieu, 35042 Rennes Cedex,

More information

Introduction to Image Super-resolution. Presenter: Kevin Su

Introduction to Image Super-resolution. Presenter: Kevin Su Introduction to Image Super-resolution Presenter: Kevin Su References 1. S.C. Park, M.K. Park, and M.G. KANG, Super-Resolution Image Reconstruction: A Technical Overview, IEEE Signal Processing Magazine,

More information

Face Hallucination Based on Eigentransformation Learning

Face Hallucination Based on Eigentransformation Learning Advanced Science and Technology etters, pp.32-37 http://dx.doi.org/10.14257/astl.2016. Face allucination Based on Eigentransformation earning Guohua Zou School of software, East China University of Technology,

More information

Super-Resolution from a Single Image

Super-Resolution from a Single Image Super-Resolution from a Single Image Daniel Glasner Shai Bagon Michal Irani Dept. of Computer Science and Applied Mathematics The Weizmann Institute of Science Rehovot 76100, Israel Abstract Methods for

More information

MULTI-POSE FACE HALLUCINATION VIA NEIGHBOR EMBEDDING FOR FACIAL COMPONENTS. Yanghao Li, Jiaying Liu, Wenhan Yang, Zongming Guo

MULTI-POSE FACE HALLUCINATION VIA NEIGHBOR EMBEDDING FOR FACIAL COMPONENTS. Yanghao Li, Jiaying Liu, Wenhan Yang, Zongming Guo MULTI-POSE FACE HALLUCINATION VIA NEIGHBOR EMBEDDING FOR FACIAL COMPONENTS Yanghao Li, Jiaying Liu, Wenhan Yang, Zongg Guo Institute of Computer Science and Technology, Peking University, Beijing, P.R.China,

More information

Video Inter-frame Forgery Identification Based on Optical Flow Consistency

Video Inter-frame Forgery Identification Based on Optical Flow Consistency Sensors & Transducers 24 by IFSA Publishing, S. L. http://www.sensorsportal.com Video Inter-frame Forgery Identification Based on Optical Flow Consistency Qi Wang, Zhaohong Li, Zhenzhen Zhang, Qinglong

More information

Selecting Models from Videos for Appearance-Based Face Recognition

Selecting Models from Videos for Appearance-Based Face Recognition Selecting Models from Videos for Appearance-Based Face Recognition Abdenour Hadid and Matti Pietikäinen Machine Vision Group Infotech Oulu and Department of Electrical and Information Engineering P.O.

More information

This is a repository copy of Face image super-resolution via weighted patches regression.

This is a repository copy of Face image super-resolution via weighted patches regression. This is a repository copy of Face image super-resolution via weighted patches regression. White Rose Research Online URL for this paper: http://eprints.whiterose.ac.uk/115963/ Version: Accepted Version

More information

Single Image Improvement using Superresolution.

Single Image Improvement using Superresolution. Single Image Improvement using Superresolution. ABSTRACT Shwetambari Shinde, Meeta Dewangan Department of Computer Science & Engineering,CSIT,Bhilai,India. shweta_shinde9388@yahoo Department of Computer

More information

Simulation and Analysis of Interpolation Techniques for Image and Video Transcoding

Simulation and Analysis of Interpolation Techniques for Image and Video Transcoding Multimedia Communication CMPE-584 Simulation and Analysis of Interpolation Techniques for Image and Video Transcoding Mid Report Asmar Azar Khan 2005-06-0003 Objective: The objective of the project is

More information

Influence of Training Set and Iterative Back Projection on Example-based Super-resolution

Influence of Training Set and Iterative Back Projection on Example-based Super-resolution Influence of Training Set and Iterative Back Projection on Example-based Super-resolution Saeid Fazli Research Institute of Modern Biological Techniques University of zanjan Zanjan, Iran Abstract Example-based

More information

Fast and Effective Interpolation Using Median Filter

Fast and Effective Interpolation Using Median Filter Fast and Effective Interpolation Using Median Filter Jian Zhang 1, *, Siwei Ma 2, Yongbing Zhang 1, and Debin Zhao 1 1 Department of Computer Science, Harbin Institute of Technology, Harbin 150001, P.R.

More information

Super-resolution using Neighbor Embedding of Back-projection residuals

Super-resolution using Neighbor Embedding of Back-projection residuals Super-resolution using Neighbor Embedding of Back-projection residuals Marco Bevilacqua, Aline Roumy, Christine Guillemot, Marie-Line Alberi Morel To cite this version: Marco Bevilacqua, Aline Roumy, Christine

More information

Edge-directed Image Interpolation Using Color Gradient Information

Edge-directed Image Interpolation Using Color Gradient Information Edge-directed Image Interpolation Using Color Gradient Information Andrey Krylov and Andrey Nasonov Laboratory of Mathematical Methods of Image Processing, Faculty of Computational Mathematics and Cybernetics,

More information

Historical Handwritten Document Image Segmentation Using Background Light Intensity Normalization

Historical Handwritten Document Image Segmentation Using Background Light Intensity Normalization Historical Handwritten Document Image Segmentation Using Background Light Intensity Normalization Zhixin Shi and Venu Govindaraju Center of Excellence for Document Analysis and Recognition (CEDAR), State

More information

EE795: Computer Vision and Intelligent Systems

EE795: Computer Vision and Intelligent Systems EE795: Computer Vision and Intelligent Systems Spring 2012 TTh 17:30-18:45 FDH 204 Lecture 14 130307 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Stereo Dense Motion Estimation Translational

More information

Robust Single Image Super-resolution based on Gradient Enhancement

Robust Single Image Super-resolution based on Gradient Enhancement Robust Single Image Super-resolution based on Gradient Enhancement Licheng Yu, Hongteng Xu, Yi Xu and Xiaokang Yang Department of Electronic Engineering, Shanghai Jiaotong University, Shanghai 200240,

More information

Graph Matching Iris Image Blocks with Local Binary Pattern

Graph Matching Iris Image Blocks with Local Binary Pattern Graph Matching Iris Image Blocs with Local Binary Pattern Zhenan Sun, Tieniu Tan, and Xianchao Qiu Center for Biometrics and Security Research, National Laboratory of Pattern Recognition, Institute of

More information

Efficient Graphical Models for Processing Images

Efficient Graphical Models for Processing Images Abstract Efficient Graphical Models for Processing Images Marshall F. Tappen Bryan C. Russell William T. Freeman Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology

More information

IMAGE SUPER-RESOLUTION BASED ON DICTIONARY LEARNING AND ANCHORED NEIGHBORHOOD REGRESSION WITH MUTUAL INCOHERENCE

IMAGE SUPER-RESOLUTION BASED ON DICTIONARY LEARNING AND ANCHORED NEIGHBORHOOD REGRESSION WITH MUTUAL INCOHERENCE IMAGE SUPER-RESOLUTION BASED ON DICTIONARY LEARNING AND ANCHORED NEIGHBORHOOD REGRESSION WITH MUTUAL INCOHERENCE Yulun Zhang 1, Kaiyu Gu 2, Yongbing Zhang 1, Jian Zhang 3, and Qionghai Dai 1,4 1 Shenzhen

More information

IMAGE RECONSTRUCTION WITH SUPER RESOLUTION

IMAGE RECONSTRUCTION WITH SUPER RESOLUTION INTERNATIONAL JOURNAL OF RESEARCH IN COMPUTER APPLICATIONS AND ROBOTICS ISSN 2320-7345 IMAGE RECONSTRUCTION WITH SUPER RESOLUTION B.Vijitha 1, K.SrilathaReddy 2 1 Asst. Professor, Department of Computer

More information

Augmented Coupled Dictionary Learning for Image Super-Resolution

Augmented Coupled Dictionary Learning for Image Super-Resolution Augmented Coupled Dictionary Learning for Image Super-Resolution Muhammad Rushdi and Jeffrey Ho Computer and Information Science and Engineering University of Florida Gainesville, Florida, U.S.A. Email:

More information

Anchored Neighborhood Regression for Fast Example-Based Super-Resolution

Anchored Neighborhood Regression for Fast Example-Based Super-Resolution Anchored Neighborhood Regression for Fast Example-Based Super-Resolution Radu Timofte 1,2, Vincent De Smet 1, and Luc Van Gool 1,2 1 KU Leuven, ESAT-PSI / iminds, VISICS 2 ETH Zurich, D-ITET, Computer

More information

ROBUST INTERNAL EXEMPLAR-BASED IMAGE ENHANCEMENT. Yang Xian 1 and Yingli Tian 1,2

ROBUST INTERNAL EXEMPLAR-BASED IMAGE ENHANCEMENT. Yang Xian 1 and Yingli Tian 1,2 ROBUST INTERNAL EXEMPLAR-BASED IMAGE ENHANCEMENT Yang Xian 1 and Yingli Tian 1,2 1 The Graduate Center, 2 The City College, The City University of New York, New York, Email: yxian@gc.cuny.edu; ytian@ccny.cuny.edu

More information

Course Evaluations. h"p:// 4 Random Individuals will win an ATI Radeon tm HD2900XT

Course Evaluations. hp://  4 Random Individuals will win an ATI Radeon tm HD2900XT Course Evaluations h"p://www.siggraph.org/courses_evalua4on 4 Random Individuals will win an ATI Radeon tm HD2900XT A Gentle Introduction to Bilateral Filtering and its Applications From Gaussian blur

More information

Structured Face Hallucination

Structured Face Hallucination 2013 IEEE Conference on Computer Vision and Pattern Recognition Structured Face Hallucination Chih-Yuan Yang Sifei Liu Ming-Hsuan Yang Electrical Engineering and Computer Science University of California

More information

Multi-scale Techniques for Document Page Segmentation

Multi-scale Techniques for Document Page Segmentation Multi-scale Techniques for Document Page Segmentation Zhixin Shi and Venu Govindaraju Center of Excellence for Document Analysis and Recognition (CEDAR), State University of New York at Buffalo, Amherst

More information

Learning Based Enhancement Model of Iris

Learning Based Enhancement Model of Iris Learning Based Enhancement Model of Iris Junzhou Huang, Li Ma, Tieniu Tan, Yunhong Wang National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, P.O. Box 2728, Beijing,

More information

Head Frontal-View Identification Using Extended LLE

Head Frontal-View Identification Using Extended LLE Head Frontal-View Identification Using Extended LLE Chao Wang Center for Spoken Language Understanding, Oregon Health and Science University Abstract Automatic head frontal-view identification is challenging

More information

INTERNATIONAL JOURNAL OF ELECTRONICS AND COMMUNICATION ENGINEERING & TECHNOLOGY (IJECET)

INTERNATIONAL JOURNAL OF ELECTRONICS AND COMMUNICATION ENGINEERING & TECHNOLOGY (IJECET) INTERNATIONAL JOURNAL OF ELECTRONICS AND COMMUNICATION ENGINEERING & TECHNOLOGY (IJECET) ISSN 0976 6464(Print) ISSN 0976 6472(Online) Volume 3, Issue 3, October- December (2012), pp. 153-161 IAEME: www.iaeme.com/ijecet.asp

More information

A A A. Fig.1 image patch. Then the edge gradient magnitude is . (1)

A A A. Fig.1 image patch. Then the edge gradient magnitude is . (1) International Conference on Information Science and Computer Applications (ISCA 013) Two-Dimensional Barcode Image Super-Resolution Reconstruction Via Sparse Representation Gaosheng Yang 1,Ningzhong Liu

More information

Super-Resolution. Many slides from Miki Elad Technion Yosi Rubner RTC and more

Super-Resolution. Many slides from Miki Elad Technion Yosi Rubner RTC and more Super-Resolution Many slides from Mii Elad Technion Yosi Rubner RTC and more 1 Example - Video 53 images, ratio 1:4 2 Example Surveillance 40 images ratio 1:4 3 Example Enhance Mosaics 4 5 Super-Resolution

More information

Nonlinear Multiresolution Image Blending

Nonlinear Multiresolution Image Blending Nonlinear Multiresolution Image Blending Mark Grundland, Rahul Vohra, Gareth P. Williams and Neil A. Dodgson Computer Laboratory, University of Cambridge, United Kingdom October, 26 Abstract. We study

More information

Example-Based Super-Resolution

Example-Based Super-Resolution Image-Based Modeling, Rendering, and Lighting Example-Based Super-Resolution Polygon-based representations of 3D objects offer resolution independence over a wide range of scales. With this approach, object

More information

Restoring Chinese Documents Images Based on Text Boundary Lines

Restoring Chinese Documents Images Based on Text Boundary Lines Proceedings of the 2009 IEEE International Conference on Systems, Man, and Cybernetics San Antonio, TX, USA - October 2009 Restoring Chinese Documents Images Based on Text Boundary Lines Hong Liu Key Laboratory

More information

DESIGN OF A NOVEL IMAGE FUSION ALGORITHM FOR IMPULSE NOISE REMOVAL IN REMOTE SENSING IMAGES BY USING THE QUALITY ASSESSMENT

DESIGN OF A NOVEL IMAGE FUSION ALGORITHM FOR IMPULSE NOISE REMOVAL IN REMOTE SENSING IMAGES BY USING THE QUALITY ASSESSMENT DESIGN OF A NOVEL IMAGE FUSION ALGORITHM FOR IMPULSE NOISE REMOVAL IN REMOTE SENSING IMAGES BY USING THE QUALITY ASSESSMENT P.PAVANI, M.V.H.BHASKARA MURTHY Department of Electronics and Communication Engineering,Aditya

More information

Robust Steganography Using Texture Synthesis

Robust Steganography Using Texture Synthesis Robust Steganography Using Texture Synthesis Zhenxing Qian 1, Hang Zhou 2, Weiming Zhang 2, Xinpeng Zhang 1 1. School of Communication and Information Engineering, Shanghai University, Shanghai, 200444,

More information

Improvement of SURF Feature Image Registration Algorithm Based on Cluster Analysis

Improvement of SURF Feature Image Registration Algorithm Based on Cluster Analysis Sensors & Transducers 2014 by IFSA Publishing, S. L. http://www.sensorsportal.com Improvement of SURF Feature Image Registration Algorithm Based on Cluster Analysis 1 Xulin LONG, 1,* Qiang CHEN, 2 Xiaoya

More information

Block-Matching based image compression

Block-Matching based image compression IEEE Ninth International Conference on Computer and Information Technology Block-Matching based image compression Yun-Xia Liu, Yang Yang School of Information Science and Engineering, Shandong University,

More information

Image Classification Using Wavelet Coefficients in Low-pass Bands

Image Classification Using Wavelet Coefficients in Low-pass Bands Proceedings of International Joint Conference on Neural Networks, Orlando, Florida, USA, August -7, 007 Image Classification Using Wavelet Coefficients in Low-pass Bands Weibao Zou, Member, IEEE, and Yan

More information

Partial Face Matching between Near Infrared and Visual Images in MBGC Portal Challenge

Partial Face Matching between Near Infrared and Visual Images in MBGC Portal Challenge Partial Face Matching between Near Infrared and Visual Images in MBGC Portal Challenge Dong Yi, Shengcai Liao, Zhen Lei, Jitao Sang, and Stan Z. Li Center for Biometrics and Security Research, Institute

More information

Robust Video Super-Resolution with Registration Efficiency Adaptation

Robust Video Super-Resolution with Registration Efficiency Adaptation Robust Video Super-Resolution with Registration Efficiency Adaptation Xinfeng Zhang a, Ruiqin Xiong b, Siwei Ma b, Li Zhang b, Wen Gao b a Institute of Computing Technology, Chinese Academy of Sciences,

More information

A Laplacian Based Novel Approach to Efficient Text Localization in Grayscale Images

A Laplacian Based Novel Approach to Efficient Text Localization in Grayscale Images A Laplacian Based Novel Approach to Efficient Text Localization in Grayscale Images Karthik Ram K.V & Mahantesh K Department of Electronics and Communication Engineering, SJB Institute of Technology, Bangalore,

More information

A NOVEL APPROACH TO ACCESS CONTROL BASED ON FACE RECOGNITION

A NOVEL APPROACH TO ACCESS CONTROL BASED ON FACE RECOGNITION A NOVEL APPROACH TO ACCESS CONTROL BASED ON FACE RECOGNITION A. Hadid, M. Heikkilä, T. Ahonen, and M. Pietikäinen Machine Vision Group Infotech Oulu and Department of Electrical and Information Engineering

More information

Fast 3D Mean Shift Filter for CT Images

Fast 3D Mean Shift Filter for CT Images Fast 3D Mean Shift Filter for CT Images Gustavo Fernández Domínguez, Horst Bischof, and Reinhard Beichel Institute for Computer Graphics and Vision, Graz University of Technology Inffeldgasse 16/2, A-8010,

More information

A Self-Learning Optimization Approach to Single Image Super-Resolution using Kernel ridge regression model

A Self-Learning Optimization Approach to Single Image Super-Resolution using Kernel ridge regression model A Self-Learning Optimization Approach to Single Image Super-Resolution using Kernel ridge regression model Ms. Dharani S 1 PG Student (CSE), Sri Krishna College of Engineering and Technology, Anna University,

More information

Face Recognition Using Ordinal Features

Face Recognition Using Ordinal Features Face Recognition Using Ordinal Features ShengCai Liao, Zhen Lei, XiangXin Zhu, ZheNan Sun, Stan Z. Li, and Tieniu Tan Center for Biometrics and Security Research & National Laboratory of Pattern Recognition,

More information

Weighted Multi-scale Local Binary Pattern Histograms for Face Recognition

Weighted Multi-scale Local Binary Pattern Histograms for Face Recognition Weighted Multi-scale Local Binary Pattern Histograms for Face Recognition Olegs Nikisins Institute of Electronics and Computer Science 14 Dzerbenes Str., Riga, LV1006, Latvia Email: Olegs.Nikisins@edi.lv

More information

Image Interpolation using Collaborative Filtering

Image Interpolation using Collaborative Filtering Image Interpolation using Collaborative Filtering 1,2 Qiang Guo, 1,2,3 Caiming Zhang *1 School of Computer Science and Technology, Shandong Economic University, Jinan, 250014, China, qguo2010@gmail.com

More information

Local Image Registration: An Adaptive Filtering Framework

Local Image Registration: An Adaptive Filtering Framework Local Image Registration: An Adaptive Filtering Framework Gulcin Caner a,a.murattekalp a,b, Gaurav Sharma a and Wendi Heinzelman a a Electrical and Computer Engineering Dept.,University of Rochester, Rochester,

More information

Shweta Gandhi, Dr.D.M.Yadav JSPM S Bhivarabai sawant Institute of technology & research Electronics and telecom.dept, Wagholi, Pune

Shweta Gandhi, Dr.D.M.Yadav JSPM S Bhivarabai sawant Institute of technology & research Electronics and telecom.dept, Wagholi, Pune Face sketch photo synthesis Shweta Gandhi, Dr.D.M.Yadav JSPM S Bhivarabai sawant Institute of technology & research Electronics and telecom.dept, Wagholi, Pune Abstract Face sketch to photo synthesis has

More information

FOREGROUND SEGMENTATION BASED ON MULTI-RESOLUTION AND MATTING

FOREGROUND SEGMENTATION BASED ON MULTI-RESOLUTION AND MATTING FOREGROUND SEGMENTATION BASED ON MULTI-RESOLUTION AND MATTING Xintong Yu 1,2, Xiaohan Liu 1,2, Yisong Chen 1 1 Graphics Laboratory, EECS Department, Peking University 2 Beijing University of Posts and

More information

Region Based Image Fusion Using SVM

Region Based Image Fusion Using SVM Region Based Image Fusion Using SVM Yang Liu, Jian Cheng, Hanqing Lu National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences ABSTRACT This paper presents a novel

More information

Edge Detection for Dental X-ray Image Segmentation using Neural Network approach

Edge Detection for Dental X-ray Image Segmentation using Neural Network approach Volume 1, No. 7, September 2012 ISSN 2278-1080 The International Journal of Computer Science & Applications (TIJCSA) RESEARCH PAPER Available Online at http://www.journalofcomputerscience.com/ Edge Detection

More information

Pictures at an Exhibition

Pictures at an Exhibition Pictures at an Exhibition Han-I Su Department of Electrical Engineering Stanford University, CA, 94305 Abstract We employ an image identification algorithm for interactive museum guide with pictures taken

More information

Interresolution Look-up Table for Improved Spatial Magnification of Image

Interresolution Look-up Table for Improved Spatial Magnification of Image Journal of Visual Communication and Image Representation 11, 360 373 (2000) doi:10.1006/jvci.1999.0451, available online at http://www.idealibrary.com on Interresolution Look-up Table for Improved Spatial

More information

An Implementation on Histogram of Oriented Gradients for Human Detection

An Implementation on Histogram of Oriented Gradients for Human Detection An Implementation on Histogram of Oriented Gradients for Human Detection Cansın Yıldız Dept. of Computer Engineering Bilkent University Ankara,Turkey cansin@cs.bilkent.edu.tr Abstract I implemented a Histogram

More information

Self-similarity Based Editing of 3D Surface Textures

Self-similarity Based Editing of 3D Surface Textures J. Dong et al.: Self-similarity based editing of 3D surface textures. In Texture 2005: Proceedings of the 4th International Workshop on Texture Analysis and Synthesis, pp. 71 76, 2005. Self-similarity

More information

A Novel Extreme Point Selection Algorithm in SIFT

A Novel Extreme Point Selection Algorithm in SIFT A Novel Extreme Point Selection Algorithm in SIFT Ding Zuchun School of Electronic and Communication, South China University of Technolog Guangzhou, China zucding@gmail.com Abstract. This paper proposes

More information

An Approach for Reduction of Rain Streaks from a Single Image

An Approach for Reduction of Rain Streaks from a Single Image An Approach for Reduction of Rain Streaks from a Single Image Vijayakumar Majjagi 1, Netravati U M 2 1 4 th Semester, M. Tech, Digital Electronics, Department of Electronics and Communication G M Institute

More information

MULTI ORIENTATION PERFORMANCE OF FEATURE EXTRACTION FOR HUMAN HEAD RECOGNITION

MULTI ORIENTATION PERFORMANCE OF FEATURE EXTRACTION FOR HUMAN HEAD RECOGNITION MULTI ORIENTATION PERFORMANCE OF FEATURE EXTRACTION FOR HUMAN HEAD RECOGNITION Panca Mudjirahardjo, Rahmadwati, Nanang Sulistiyanto and R. Arief Setyawan Department of Electrical Engineering, Faculty of

More information

A Hierarchial Model for Visual Perception

A Hierarchial Model for Visual Perception A Hierarchial Model for Visual Perception Bolei Zhou 1 and Liqing Zhang 2 1 MOE-Microsoft Laboratory for Intelligent Computing and Intelligent Systems, and Department of Biomedical Engineering, Shanghai

More information

The Proposal of a New Image Inpainting Algorithm

The Proposal of a New Image Inpainting Algorithm The roposal of a New Image Inpainting Algorithm Ouafek Naouel 1, M. Khiredinne Kholladi 2, 1 Department of mathematics and computer sciences ENS Constantine, MISC laboratory Constantine, Algeria naouelouafek@yahoo.fr

More information

GRID WARPING IN TOTAL VARIATION IMAGE ENHANCEMENT METHODS. Andrey Nasonov, and Andrey Krylov

GRID WARPING IN TOTAL VARIATION IMAGE ENHANCEMENT METHODS. Andrey Nasonov, and Andrey Krylov GRID WARPING IN TOTAL VARIATION IMAGE ENHANCEMENT METHODS Andrey Nasonov, and Andrey Krylov Lomonosov Moscow State University, Moscow, Department of Computational Mathematics and Cybernetics, e-mail: nasonov@cs.msu.ru,

More information

SELECTION OF THE OPTIMAL PARAMETER VALUE FOR THE LOCALLY LINEAR EMBEDDING ALGORITHM. Olga Kouropteva, Oleg Okun and Matti Pietikäinen

SELECTION OF THE OPTIMAL PARAMETER VALUE FOR THE LOCALLY LINEAR EMBEDDING ALGORITHM. Olga Kouropteva, Oleg Okun and Matti Pietikäinen SELECTION OF THE OPTIMAL PARAMETER VALUE FOR THE LOCALLY LINEAR EMBEDDING ALGORITHM Olga Kouropteva, Oleg Okun and Matti Pietikäinen Machine Vision Group, Infotech Oulu and Department of Electrical and

More information

Novel Iterative Back Projection Approach

Novel Iterative Back Projection Approach IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661, p- ISSN: 2278-8727Volume 11, Issue 1 (May. - Jun. 2013), PP 65-69 Novel Iterative Back Projection Approach Patel Shreyas A. Master in

More information

CORRELATION BASED CAR NUMBER PLATE EXTRACTION SYSTEM

CORRELATION BASED CAR NUMBER PLATE EXTRACTION SYSTEM CORRELATION BASED CAR NUMBER PLATE EXTRACTION SYSTEM 1 PHYO THET KHIN, 2 LAI LAI WIN KYI 1,2 Department of Information Technology, Mandalay Technological University The Republic of the Union of Myanmar

More information

Gabor Surface Feature for Face Recognition

Gabor Surface Feature for Face Recognition Gabor Surface Feature for Face Recognition Ke Yan, Youbin Chen Graduate School at Shenzhen Tsinghua University Shenzhen, China xed09@gmail.com, chenyb@sz.tsinghua.edu.cn Abstract Gabor filters can extract

More information

Face Detection using Hierarchical SVM

Face Detection using Hierarchical SVM Face Detection using Hierarchical SVM ECE 795 Pattern Recognition Christos Kyrkou Fall Semester 2010 1. Introduction Face detection in video is the process of detecting and classifying small images extracted

More information

Light Field Occlusion Removal

Light Field Occlusion Removal Light Field Occlusion Removal Shannon Kao Stanford University kaos@stanford.edu Figure 1: Occlusion removal pipeline. The input image (left) is part of a focal stack representing a light field. Each image

More information

Efficient Image Compression of Medical Images Using the Wavelet Transform and Fuzzy c-means Clustering on Regions of Interest.

Efficient Image Compression of Medical Images Using the Wavelet Transform and Fuzzy c-means Clustering on Regions of Interest. Efficient Image Compression of Medical Images Using the Wavelet Transform and Fuzzy c-means Clustering on Regions of Interest. D.A. Karras, S.A. Karkanis and D. E. Maroulis University of Piraeus, Dept.

More information

A Log-Polar Interpolation Applied to Image Scaling

A Log-Polar Interpolation Applied to Image Scaling IEEE International Workshop on Imaging Systems and Techniques IST 2007 Krakow, Poland, May 4 5, 2007 A Log-Polar Interpolation Applied to Image Scaling A. Amanatiadis 1, I. Andreadis 1, A. Gasteratos 2

More information

Ms.DHARANI SAMPATH Computer Science And Engineering, Sri Krishna College Of Engineering & Technology Coimbatore, India

Ms.DHARANI SAMPATH Computer Science And Engineering, Sri Krishna College Of Engineering & Technology Coimbatore, India Improving Super Resolution of Image by Multiple Kernel Learning Ms.DHARANI SAMPATH Computer Science And Engineering, Sri Krishna College Of Engineering & Technology Coimbatore, India dharanis012@gmail.com

More information

Object detection using non-redundant local Binary Patterns

Object detection using non-redundant local Binary Patterns University of Wollongong Research Online Faculty of Informatics - Papers (Archive) Faculty of Engineering and Information Sciences 2010 Object detection using non-redundant local Binary Patterns Duc Thanh

More information

Latest development in image feature representation and extraction

Latest development in image feature representation and extraction International Journal of Advanced Research and Development ISSN: 2455-4030, Impact Factor: RJIF 5.24 www.advancedjournal.com Volume 2; Issue 1; January 2017; Page No. 05-09 Latest development in image

More information

3D Modeling from Multiple Images

3D Modeling from Multiple Images 3D Modeling from Multiple Images Wei Zhang 1,JianYao 2, and Wai-Kuen Cham 1 1 Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong SAR, China 2 College of

More information

arxiv: v1 [cs.cv] 23 Aug 2017

arxiv: v1 [cs.cv] 23 Aug 2017 Single Reference Image based Scene Relighting via Material Guided Filtering Xin Jin a, Yannan Li a, Ningning Liu c, Xiaodong Li a,, Xianggang Jiang a, Chaoen Xiao b, Shiming Ge d, arxiv:1708.07066v1 [cs.cv]

More information

Graph-Based Superpixel Labeling for Enhancement of Online Video Segmentation

Graph-Based Superpixel Labeling for Enhancement of Online Video Segmentation Graph-Based Superpixel Labeling for Enhancement of Online Video Segmentation Alaa E. Abdel-Hakim Electrical Engineering Department Assiut University Assiut, Egypt alaa.aly@eng.au.edu.eg Mostafa Izz Cairo

More information

Blind Measurement of Blocking Artifact in Images

Blind Measurement of Blocking Artifact in Images The University of Texas at Austin Department of Electrical and Computer Engineering EE 38K: Multidimensional Digital Signal Processing Course Project Final Report Blind Measurement of Blocking Artifact

More information

Palm Vein Recognition with Local Binary Patterns and Local Derivative Patterns

Palm Vein Recognition with Local Binary Patterns and Local Derivative Patterns Palm Vein Recognition with Local Binary Patterns and Local Derivative Patterns Leila Mirmohamadsadeghi and Andrzej Drygajlo Swiss Federal Institude of Technology Lausanne (EPFL) CH-1015 Lausanne, Switzerland

More information

Super Resolution Using Graph-cut

Super Resolution Using Graph-cut Super Resolution Using Graph-cut Uma Mudenagudi, Ram Singla, Prem Kalra, and Subhashis Banerjee Department of Computer Science and Engineering Indian Institute of Technology Delhi Hauz Khas, New Delhi,

More information

Single Image Super-Resolution via Iterative Collaborative Representation

Single Image Super-Resolution via Iterative Collaborative Representation Single Image Super-Resolution via Iterative Collaborative Representation Yulun Zhang 1(B), Yongbing Zhang 1, Jian Zhang 2, aoqian Wang 1, and Qionghai Dai 1,3 1 Graduate School at Shenzhen, Tsinghua University,

More information

Direction-Length Code (DLC) To Represent Binary Objects

Direction-Length Code (DLC) To Represent Binary Objects IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661,p-ISSN: 2278-8727, Volume 18, Issue 2, Ver. I (Mar-Apr. 2016), PP 29-35 www.iosrjournals.org Direction-Length Code (DLC) To Represent Binary

More information

Integration of Multiple-baseline Color Stereo Vision with Focus and Defocus Analysis for 3D Shape Measurement

Integration of Multiple-baseline Color Stereo Vision with Focus and Defocus Analysis for 3D Shape Measurement Integration of Multiple-baseline Color Stereo Vision with Focus and Defocus Analysis for 3D Shape Measurement Ta Yuan and Murali Subbarao tyuan@sbee.sunysb.edu and murali@sbee.sunysb.edu Department of

More information

Self-Learning of Edge-Preserving Single Image Super-Resolution via Contourlet Transform

Self-Learning of Edge-Preserving Single Image Super-Resolution via Contourlet Transform Self-Learning of Edge-Preserving Single Image Super-Resolution via Contourlet Transform Min-Chun Yang, De-An Huang, Chih-Yun Tsai, and Yu-Chiang Frank Wang Dept. Computer Science and Information Engineering,

More information

Analysis of Image and Video Using Color, Texture and Shape Features for Object Identification

Analysis of Image and Video Using Color, Texture and Shape Features for Object Identification IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661,p-ISSN: 2278-8727, Volume 16, Issue 6, Ver. VI (Nov Dec. 2014), PP 29-33 Analysis of Image and Video Using Color, Texture and Shape Features

More information

Adaptive Fuzzy Watermarking for 3D Models

Adaptive Fuzzy Watermarking for 3D Models International Conference on Computational Intelligence and Multimedia Applications 2007 Adaptive Fuzzy Watermarking for 3D Models Mukesh Motwani.*, Nikhil Beke +, Abhijit Bhoite +, Pushkar Apte +, Frederick

More information

Single-image super-resolution in RGB space via group sparse representation

Single-image super-resolution in RGB space via group sparse representation Published in IET Image Processing Received on 10th April 2014 Revised on 22nd September 2014 Accepted on 15th October 2014 ISSN 1751-9659 Single-image super-resolution in RGB space via group sparse representation

More information